Deep Workpiece Region Segmentation for Bin Picking

  title={Deep Workpiece Region Segmentation for Bin Picking},
  author={Muhammad Usman Khalid and Janik M. Hager and Werner Kraus and Marco F. Huber and Marc Toussaint},
  journal={2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)},
For most industrial bin picking solutions, the pose of a workpiece is localized by matching a CAD model to point cloud obtained from 3D sensor. Distinguishing flat workpieces from bottom of the bin in point cloud imposes challenges in the localization of workpieces that lead to wrong or phantom detections. In this paper, we propose a framework that solves this problem by automatically segmenting workpiece regions from non-workpiece regions in a point cloud data. It is done in real time by… Expand
Multiple Object Detection of Workpieces Based on Fusion of Deep Learning and Image Processing*
A workpiece detection method based on fusion of deep learning and image processing effectively corrects the bounding boxes obtained by deep learning, and obtains workpiece contour and gripping point information. Expand
One-Shot Shape-Based Amodal-to-Modal Instance Segmentation
OSSIS is proposed, a single-stage One-Shot Shape-based Instance Segmentation algorithm that produces the target object modal segmentation mask in a depth image of a scene based only on a binary shape mask of thetarget object. Expand


Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Point Clouds
A method for automated dataset generation and rapidly generate a training dataset of 50k depth images and 320k object masks synthetically using simulated scenes of 3D CAD models is presented and a variant of Mask R-CNN is trained on the generated dataset to perform category-agnostic instance segmentation without hand-labeled data. Expand
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
  • Yin Zhou, Oncel Tuzel
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VoxelNet is proposed, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network and learns an effective discriminative representation of objects with various geometries, leading to encouraging results in3D detection of pedestrians and cyclists. Expand
Object Pose Detection in Industrial Environment
This paper shows a method for object pose detection that is successfully applied to industrial applications running a three-shift system and showed its usability regarding the crucial requirements, such as robustness, accuracy, portability and speed. Expand
RGB-D object detection and semantic segmentation for autonomous manipulation in clutter
The experiments show that object detection and semantic segmentation complement each other and can be combined to yield reliable object perception. Expand
Object recognition: Bin-picking for industrial use
A method for object pose detection and gripping point determination that is successfully applied to industrial applications running a three-shift system showed its usability regarding the crucial requirements, such as robustness, accuracy, portability and speed. Expand
Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds
A deep learning architecture is presented which addresses the problem of 3D semantic segmentation of unstructured point clouds and introduces grouping techniques which define point neighborhoods in the initial world space and the learned feature space. Expand
Segmentation and Location Computation of Bin Objects
The vision system is found to be effective for partially occluded objects, in the absence of albedo effects, and validated through real time bin picking experiments on the Adept Robot. Expand
Mask R-CNN
This work presents a conceptually simple, flexible, and general framework for object instance segmentation that outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. Expand
Understanding Convolution for Semantic Segmentation
DUC is designed to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling, and a hybrid dilated convolution (HDC) framework in the encoding phase is proposed. Expand
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. Expand